GenPark LLM Token Bucket & Sliding Window Rate Limiter
LocalAbout GenPark LLM Token Bucket & Sliding Window Rate Limiter
A Python MCP server for managing LLM token and request rates with adaptive multi-tier limits, leaky-bucket queuing, and burst-wait estimates. It is intended for workflows that need to regulate TPM and RPM usage.
Key features
- 01Adaptive multi-tier TPM and RPM limits
- 02Leaky-bucket queuing
- 03Burst wait estimation
- 04Python 3 standard-library implementation
Use cases
- 01Regulating TPM usage
- 02Regulating RPM usage
MCP support
Runs as an MCP server that can be added to Claude Desktop or Cursor configuration. Its stated function is rate limiting for LLM token and request usage.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEgenpark-llm-token-bucket-sliding-window-rate-limiter-skill
Adaptive multi-tier TPM and RPM rate limiter with smooth leaky bucket queuing and predictive burst wait estimation
Quick Installation & MCP Integration
Add to your Claude Desktop or Cursor configuration:
{
"mcpServers": {
"genpark-llm-token-bucket-sliding-window-rate-limiter-skill": {
"command": "python",
"args": ["mcp_server.py"]
}
}
}
Zero Dependencies
Implemented entirely in Python 3 standard library.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.